Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4132 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.9137. Min Act: -0.1700
Data Index: 3565256 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.8512. Min Act: -0.1700
Data Index: 5733648 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.7887. Min Act: -0.1700
Data Index: 5613444 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.6325. Min Act: -0.1700
Data Index: 6617194 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.5700. Min Act: -0.1700
Data Index: 1948912 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.5075. Min Act: -0.1700
Data Index: 7225837 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.5075. Min Act: -0.1700
Data Index: 5169603 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4450. Min Act: -0.1700
Data Index: 1384032 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4762. Min Act: -0.1700
Data Index: 7399104 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4762. Min Act: -0.1700
Data Index: 8532920 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4762. Min Act: -0.1700
Data Index: 6782919 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3188312 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4137. Min Act: -0.1700
Data Index: 3708922 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1681242 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1147938 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.3825. Min Act: -0.1700
Data Index: 4234905 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.3825. Min Act: -0.1700
Data Index: 27317 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.3825. Min Act: -0.1700
Data Index: 8281061 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.3512. Min Act: -0.1700
Data Index: 5252554 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9137. Min Range: -4.9137
Max Act: 4.3200. Min Act: -0.1700
Data Index: 2589273 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19